ewald1976/nemo-crownelius-st-12b
Same weights, converted vs mistralai/Mistral-Nemo-Instruct-2407. Same weights stored in another dtype (BF16 → F16).
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1
2 derivatives checked
- mradermacher/nemo-crownelius-st-12b-i1-GGUF: Quantization
- mradermacher/nemo-crownelius-st-12b-GGUF: Quantization